Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3998 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2649. Min Act: -0.0001

Data Index: 196285 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2575. Min Act: -0.0001

Data Index: 44877 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2831. Min Act: -0.0001

Data Index: 237353 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2691. Min Act: -0.0001

Data Index: 109994 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2704. Min Act: -0.0001

Data Index: 390886 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2397. Min Act: -0.0001

Data Index: 43388 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2422. Min Act: -0.0001

Data Index: 282323 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2483. Min Act: -0.0001

Data Index: 1087544 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2140. Min Act: -0.0001

Data Index: 566171 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2182. Min Act: -0.0001

Data Index: 730284 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2015. Min Act: -0.0001

Data Index: 997087 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1828. Min Act: -0.0001

Data Index: 552344 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1256908 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.2001. Min Act: -0.0001

Data Index: 587828 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1753. Min Act: -0.0001

Data Index: 28587 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1817. Min Act: -0.0001

Data Index: 555519 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1845. Min Act: -0.0001

Data Index: 1295456 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1555. Min Act: -0.0001

Data Index: 49585 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1135560 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.2831. Min Range: -0.2831

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1023584 (C4 (Web Text))

Max Activating Token Index: 239